INDEX

Explanations

terms related to ligaments or ligaments-related concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to sports, particularly football (soccer), and associated regulations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Heard

-0.77

 Hiroshima

-0.72

 Alma

-0.71

 Augusta

-0.70

Downloadha

-0.69

WS

-0.67

 Magnum

-0.66

 squared

-0.65

 Remastered

-0.65

 Shutterstock

-0.63

POSITIVE LOGITS

lig

1.09

atory

1.06

reements

1.00

entials

1.00

eties

0.99

ibility

0.98

archs

0.95

atures

0.93

ration

0.93

acy

0.92

Activations Density 0.011%

terms related to ligaments or ligaments-related concepts

terms related to sports, particularly football (soccer), and associated regulations

No Comments

No Known Activations